Plugins

Policy-layer guard that checks tool calls before they run: a read whitelist, a sensitive-path deny list (credentials, browser profiles, chat history, other users' home directories), dangerous-command blocking, subagent isolation, and a static scan that quarantines executables. Every denial is appended to an audit log. It is a text-and-path filter, not a sandbox or antivirus: dynamically built paths, encoded payloads and packed binaries can get past it, and it does not replace the OS antivirus.

Brings the rtk token-saving setup from Claude Code to DeepSeek Harness: commands rtk can rewrite are rewritten, and builds, tests and logs it cannot reach are compressed; git, cargo, npm and pytest are covered. Compressed output tells the model what was elided and how to recover it; when the sandbox cannot reach the rtk store the original is saved and its path given. Savings show without a command: a pill below the composer, with `/rtk stats` for detail. When a rewrite is unreliable the original command runs as usual: if rtk cannot run, or the returned command would drop arguments, nothing breaks. The rtk binary ships with the package, so mainstream platforms need no separate rtk install, unlike most other rtk plugins.

Compares installed plugins against a downloaded DSH update and reports which interfaces they use that the update no longer exposes. Runs before you install, with a dry-run diagnose command for when it declines to act. Windows only, on the DSH desktop app, with Node.js 18+.

Multi-channel push notification plugin supporting Bark (iOS) and ntfy (Android/iOS/Web/Desktop) for turn completion, approvals, questions, and quota halts.

GitLab panel in the DSH right sidebar: commit graph, branches, changes, merge requests (inline diffs, review submission, pipelines), issues, and agent tools with an approval queue for triage and batch actions. GitLab data needs a personal access token or a logged-in `glab`; local git data works without either.

Config-driven lifecycle hooks for DSH: block or observe tool calls, and react to completed turns, messages, and title changes with shell commands.

Plot decision gate for novel writing: five beat_* tools register each node that changes the story into a decision point with 2-4 divergent options, beat_gate returns pass:false until the author picks, and beat_compile turns the picks into a chapter outline.

HarmonyOS delivery orchestration for DSH: freezes a four-dimension acceptance pack whose measurable criteria carry machine-checkable assertions, runs an adversarial pre-review before dispatch, hands the work to DevEco Code in Goal mode, then audits the delivery with independently gathered evidence (screenshots, UI tree, logs, hashed evidence bundle), recomputing assertion verdicts against measured values and filing rework orders; includes a cited rule catalog, a user-confirmation state and a gate calibration ledger.

Deck-generation skill for the National College Student Career Planning Competition. It takes a contestant's profile, materials and photographs, drafts a page-by-page outline for confirmation, then renders a 15-20 page reading-type PPTX (under 15 pages is flagged as a page-count error) using 17 page types, three built-in themes or a user-supplied template; the build audits the estimated layout (text overflow, per-page word count, missing evaluation dimensions, material gaps) and the rendered PDF is checked again for out-of-bounds and overlapping text. Requires Python 3.9+ with python-pptx, python-docx and Pillow; LibreOffice (soffice) and pdftotext are optional for the PDF layout re-check.

Group skills into named sets, toggle any combination, drag to reorder, and preview each group catalog token cost.

Whole-PDF paper translation for DSH on top of a BabelDOC installation you provide (Python CLI, with an OpenAI-compatible API key in its config.toml): bilingual dual-page output, a token cost estimate before running, a per-domain glossary reused across papers, and the server-side thinking overhead disabled for translation.

An AI reading buddy: it sits next to you while you read, and only knows the pages you have already reached — so it cannot spoil the rest, and it never summarizes the whole book for you. Highlight a sentence and ask about it, or just ask about what you finished; it usually restates what you seem to mean and asks one concrete question back. What you work out can be saved as a takeaway and later becomes a review card that jumps back to the sentence. EPUB, MOBI, FB2, TXT, Markdown, HTML, CBZ.

Compiles a repository into a source-grounded code map: structured pages where every claim carries a verifiable path:line citation, an interactive dependency graph, knowledge cards, four model tools and the /codemap command. Deterministic, no model calls, zero dependencies.

GitHub Trending radar inside the Harness Web UI: fetches the daily, weekly or monthly board (optionally filtered by a language), analyzes each repository into description, star gain, tech stack, highlights and risks, renders the result as a filterable card panel with paging, and registers the github_trending tool plus the /github-trending command.

Answers Dark Souls III questions from your own Windows PC save (default `%APPDATA%\DarkSoulsIII\*\DS30000.sl2`): level and stats, current area, bonfires/rings/spells/covenants counted by family, kill state for the 24 bosses, and Steam achievements when Steam is installed - exposed as model tools plus a progress pill beside the composer and a 19-area sidebar page with next-step suggestions. The save stays read-only and is parsed locally by a bundled Python 3 script; Python 3 and the `cryptography` package must be installed, and the game data ships with the plugin.

Publishes and reads QQ Zone posts through SnowLuma's OneBot qzone_* actions (SnowLuma 2.2+ signed in to QQ), and lets the agent understand images with a local vision model (OpenAI-compatible gateway) or Windows OCR.

Turn a script into a narrated explainer video: text-card slides by default (fast and exact for tutorials) or AI-generated footage per segment (needs AGNES_API_KEY); 14 online neural Chinese voices plus 3 offline Windows voices, with a one-command sample pack for picking a voice by ear. Requires ffmpeg, and the bundled video-remix skill copied to <workspace>/.dsh/skills/video-remix with npm install run there for the online voices.

Compiles LaTeX with the TeX Live installed on the machine: one `latex` tool typesets a formula into an SVG, PNG or PDF and a whole document into a PDF (Chinese text switches to xelatex with ctexart), writes the file into the workspace and returns a Markdown reference to it. A system-prompt section asks the model to write `$...$` and `$$...$$` instead of code fences, and when no TeX Live is found a banner above the composer offers a one-click BasicTeX or TinyTeX install.

Claude Code-compatible persistent memory: the host injects the MEMORY.md index at session start, the model maintains memory files with plain read/write/edit tools, and a Settings page lists saved memories. Same on-disk format as Claude Code; claude mode shares the exact memory directory.

An intercom between already-open DSH windows. No teams, no new sessions, just peer-to-peer messages with a hop limit.

Precomputes the compaction summary in the background and commits the held result when pressure compaction fires, removing the foreground model round-trip. Registers itself as the session compaction engine, pins the span it summarised so the payload fingerprint still matches at commit time, prunes tool results before committing, and falls back to the stock foreground path on payload drift or context overflow.

Read-only export of a chat.deepseek.com conversation into a new DSH session: builds a hand-off pack with the selected rounds kept verbatim and earlier rounds collapsed to one line each, then pre-fills the composer without sending it. Windows only as published (package.json os=win32); requires Edge or Chrome and a one-time chat.deepseek.com login.

Rewinds a finished turn in place — a button next to your own message withdraws that message and everything after it from the model context, puts its text back in the composer for editing, and optionally restores the files the turn changed through the DSH filesystem service.

Turns the composer's model menu into a two-level list (provider first, then that provider's models), shows the current model together with its provider name, asks for a reasoning effort after a model is picked, and adds settings switches that hide whole providers or single models from the picker.